Automatic clustering for self-organizing grids
US8041773B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 23, 2008 |
| Grant date | Oct 18, 2011 |
| Priority date | — |
| Expiry date | Sep 5, 2029 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L67/51
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
Computational grids have traditionally not scaled effectively due to administrative hurdles to resource and user participation. Most production grids are essentially multi-site supercomputer centers, rather than truly open and heterogeneous sets of resources that can join and leave dynamically, and that can provide support for an equally dynamic set of users. Large-scale grids containing individual resources with more autonomy about when and how they join and leave will require self-organizing grid middleware services that do not require centralized administrative control. Dynamic discovery of high-performance variable-size clusters of grid nodes provides an effective solution for implementation of grids. A brute force approach to the problem of identifying these “ad-hoc clusters” would require excessive overhead in terms of both message exchange and computation. Therefore, a scalable solution is provided that uses a delay-based overlay structure to organize nodes based on their proximity to one another, using a small number of delay experiments. This overlay can then be used to provide a variable-size set of promising candidate nodes than can then be used as a cluster, or tested f…
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.